Back to skill

Security audit

Academic Research Hub Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a simple academic research guidance skill with no code, persistence, or hidden execution, though its paywall wording should be interpreted strictly as lawful access only.

Before installing, understand that this skill is only appropriate for lawful academic research workflows. Use it to find open-access papers, DOIs, preprints, library or institutional access paths, and citation data; do not use it to evade paywalls, bypass access controls, or violate publisher terms.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly lists 'access paywalled papers' as a supported use case without any guardrails about lawful access, licensing, or institutional permissions. This can normalize or encourage unauthorized access workflows and create legal, policy, and compliance risk for users and downstream agents.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Advertising 'Paywall bypass suggestions (legal alternatives)' is risky because 'paywall bypass' language can steer users or agents toward circumvention behavior even if the parenthetical attempts to narrow scope. Without explicit constraints, the skill may be interpreted as permitting assistance that violates copyright, contracts, or platform acceptable-use rules.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.